Problem about the normalization part

floodsung / LearningToCompare_FSL

PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Few-Shot Learning part)

MIT License

1.04k stars 268 forks source link

Problem about the normalization part #7

Closed MathildaChen closed 6 years ago

MathildaChen commented 6 years ago

Thank you for your awesome code. There is a norm part for both miniimagenet and omniglot data, "normalize = transforms.Normalize(mean=[0.92206, 0.92206, 0.92206], std=[0.08426, 0.08426, 0.08426])" but why are the the mean and std values always the same?

floodsung commented 6 years ago

We just keep image data with 3d have the same mean and std. It is a common process on Imagenet.